Autonomous Learning Engineer

Job Summary

We are seeking an Autonomous Learning Engineer to design, train, and deploy reinforcement learning (RL) solutions for complex decision-making systems. The ideal candidate will have expertise in Python, deep learning, reinforcement learning, simulation environments, RLHF, and distributed training, with experience building scalable, production-ready AI solutions.

Key Responsibilities

• Design and implement reinforcement learning solutions for real-world applications
• Develop and optimize simulation environments and RL training pipelines
• Implement and evaluate modern RL algorithms and reward models
• Improve model performance, training stability, and sample efficiency
• Collaborate with AI and product teams to deploy production-ready RL solutions
• Monitor deployed models and ensure reliability, safety, and continuous improvement

Required Qualifications

• 6+ years of experience in reinforcement learning research and engineering
• Strong proficiency in Python and modern deep learning frameworks
• Experience with RL libraries, simulation environments, GPU-based training, and distributed learning
• Strong understanding of reinforcement learning, optimization, and probability

Preferred Qualifications

• Experience with RLHF, multi-agent RL, robotics, autonomous systems, or control systems
• Publications or open-source contributions in reinforcement learning